1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
|
"""
A reply names the request it answers.
MNP carried no correlation id until 2026-09-07. A reply named its own type and
nothing else, so a client with more than one request outstanding had to work out
which one a message answered from the message itself — and for the replies that
name nothing, it could not. This module sends `{"type": "error"}` from 240
places and two of them say what they are about; `_dispatch_message`'s catch-all
is one of the 238. Such a refusal reached no caller at all: the browser handed
it to whichever request happened to be waiting, and the request it belonged to
sat until its own 30s timeout. Live symptom (2026-09-06): the Chat composer is
disabled while a send is in flight, so a chat message whose refusal went astray
froze the tab for thirty seconds.
`req_id` is the client's own pending-map key, put on the wire and stamped back
onto the reply by `_send`. What matters here, and what the browser cannot check
for itself:
* a reply carries it, including the refusals that name nothing else;
* a *broadcast* does not — it answers no request, and stamping it would hand
another peer's client a reply to a request it never made;
* work handed to a background task still answers under the right id, which is
why this is a ContextVar and not an attribute on the session.
"""
import asyncio
import msgpack
import pytest
from meshbay_common.protocol import MNP
from meshbay_node.transport.webrtc_server import WebRTCPeerSession
pytestmark = pytest.mark.asyncio
class _Channel:
readyState = "open"
def __init__(self):
self.sent = []
def send(self, framed):
# Skip the 4-byte length prefix _pack writes.
self.sent.append(msgpack.unpackb(framed[4:], raw=False))
def _session(peer_id="p"):
s = WebRTCPeerSession.__new__(WebRTCPeerSession)
s._ctx = {}
s._peer_id = peer_id
s._user_id = None
s._group_id = ""
s._channel = _Channel()
s._tasks = set()
return s
async def test_a_refusal_that_names_nothing_else_names_the_request():
"""The reply at the root of the defect: no type of its own to match on."""
s = _session()
# No handshake yet, so any other message is refused — a bare `error`, the
# same shape the catch-all sends and the same shape a browser could not
# route.
s._handle_message({"type": MNP.CHAT_MESSAGE, "req_id": 41})
(reply,) = s._channel.sent
assert reply["type"] == "error"
assert reply["req_id"] == 41, (
"a refusal that names neither the request nor a type of its own is a "
"reply no caller can claim")
async def test_the_catch_all_refusal_names_the_request_too():
"""Every failure in the dispatch loop funnels into one generic reply."""
s = _session()
s._user_id = "u"
def _boom(msg):
raise RuntimeError("filesystem path that must not reach the peer")
s._do_chat_message = _boom
s._handle_message({"type": MNP.CHAT_MESSAGE, "req_id": 7})
(reply,) = s._channel.sent
assert reply == {"type": "error", "detail": "Request failed", "req_id": 7}, (
"the catch-all is where an unforeseen failure ends up, so it is exactly "
"the reply that must still be routable")
async def test_a_request_without_an_id_is_answered_without_one():
"""An older client sends none; nothing may be invented for it."""
s = _session()
s._handle_message({"type": MNP.CHAT_MESSAGE})
(reply,) = s._channel.sent
assert "req_id" not in reply
async def test_a_broadcast_to_another_peer_is_not_stamped():
"""The reply goes to the asker; the broadcast goes to everyone else.
They travel out of the same handler, and only the first answers anything.
Stamping the second would hand another browser a reply keyed to a pending
request of its own that it never sent — the very confusion this fixes.
"""
asker, other = _session("asker"), _session("other")
asker._user_id, other._user_id = "a", "b"
registry = {"a": asker, "b": other}
asker._peer_registry = lambda: registry
asker._user_names = lambda: {}
asker._audit = lambda *a, **k: None
asker._group_ctx = lambda: {}
asker._handle_message({"type": MNP.CHAT_MESSAGE, "payload": "hi", "req_id": 3})
(ack,) = asker._channel.sent
assert ack["type"] == "ack" and ack["req_id"] == 3
(broadcast,) = other._channel.sent
assert broadcast["type"] == MNP.CHAT_MESSAGE
assert "req_id" not in broadcast, (
"a broadcast answers no request and must not look like a reply")
async def test_work_handed_to_a_task_still_answers_under_the_right_id():
"""Most handlers `_spawn` their real work, and the reply leaves long after
the dispatch call that started it has returned.
This is the reason the id lives in a ContextVar: asyncio copies the current
context into a task, so the answer keeps the id even though nothing passed
it along. An attribute on the session would have been overwritten by the
next message to arrive in the meantime.
"""
s = _session()
s._user_id = "u"
async def _late(reply):
await asyncio.sleep(0.01)
s._send({"type": "roster_read_resp", "detail": reply})
s._do_chat_message = lambda msg: s._spawn(_late(msg["payload"]))
s._handle_message({"type": MNP.CHAT_MESSAGE, "payload": "first", "req_id": 11})
# A second request arrives while the first one's task is still asleep.
s._handle_message({"type": MNP.CHAT_MESSAGE, "payload": "second", "req_id": 12})
await asyncio.gather(*list(s._tasks))
by_id = {m["req_id"]: m["detail"] for m in s._channel.sent}
assert by_id == {11: "first", 12: "second"}, (
"a late reply answered under whichever request arrived most recently")
|